Weak-current intelligent lighting system with intelligent dimming and energy-saving control functions

Abstract

The invention discloses a weak current intelligent lighting system with intelligent dimming and energy-saving control, and relates to the technical field of industrial plant lighting control, the system divides a plant into a plurality of marked areas, collects illumination, power, infrared and meteorological multi-source data in real time, combines feature fusion and a time sequence interpolation algorithm, and constructs a structured data set; a deep learning model is utilized, natural light, illumination power and operation requirements are fused, and dynamic generation and energy-saving control of a regional illumination strategy are achieved; the system calculates an environment illumination difference coefficient HJZD, an operation task matching illumination coefficient ZYZx and a load balancing energy consumption coefficient FZNH, compares the environment illumination difference coefficient HJZD, the operation task matching illumination coefficient ZYZx and the load balancing energy consumption coefficient FZNH with corresponding thresholds Q1, Q2 and Q3, judges whether natural light utilization, task illumination matching and the overall energy efficiency state are qualified or not, and outputs a targeted illumination adjustment strategy. And the intelligent level and the energy consumption utilization efficiency of industrial factory building illumination are obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial plant lighting control, and in particular to a weak-current intelligent lighting system with intelligent dimming and energy-saving control. Background Art

[0002] Currently, industrial plants, as the primary space for high-intensity operations, place higher demands on the stability, adaptability, and energy control of lighting systems. Traditional industrial lighting solutions are plagued by the following issues: First, the lighting system lacks effective utilization of natural light resources, maintaining full power even when natural light intensity is high, resulting in energy waste. Second, the lighting strategy cannot be dynamically adjusted based on the type of task and the presence of personnel, resulting in frequent redundant or insufficient illumination, impacting operational efficiency and employee health. Third, the uneven distribution of lighting loads across different areas and the lack of a unified coordination mechanism can easily lead to energy consumption deviations and system operation anomalies, making it difficult to achieve coordinated energy-saving control of lighting across the entire area.

[0003] With the continued advancement of smart manufacturing and green factory concepts, lighting systems are gradually developing towards intelligent, modular, and data-driven approaches. Some factories have attempted to deploy devices such as light sensors and automatic dimming lamps, but these are often limited to single-point control or preset rules, making it difficult to implement global intelligent lighting strategies based on real-time scene perception and adaptive operation behavior. Furthermore, existing energy-saving control systems generally ignore the deep integration and utilization of multi-source heterogeneous information, such as natural light disturbance factors, window structure parameters, personnel layout characteristics, and regional energy consumption history, and lack the algorithmic models to support the generation of intelligent strategies. Summary of the Invention

[0004] In view of the deficiencies in the prior art, the present invention provides a weak-current intelligent lighting system with intelligent dimming and energy-saving control to solve the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a weak current intelligent lighting system with intelligent dimming and energy-saving control, including a data acquisition module, a data processing module, an AI illumination dynamic adjustment model establishment module, an ambient light monitoring module, an operation task adaptive monitoring module and a global lighting load energy efficiency monitoring module; The data acquisition module is used to collect environmental data, lighting data and behavioral comprehensive data in real time by dividing the industrial plant into multiple marked areas and deploying light, power, infrared and meteorological sensing equipment in each area; The data processing module is used to normalize, filter and time-align the multi-source collected data using feature fusion and time series interpolation algorithms, and obtain a structured feature data set; The AI ​​illuminance dynamic adjustment model establishment module is used to build a deep learning model that integrates natural light, lighting power, and operational requirements based on structured feature dataset data and historical samples. It has environmental perception, task adaptation, and energy consumption balance capabilities, and realizes adaptive generation and energy-saving control of multi-area lighting strategies. The ambient light monitoring module is used to monitor the natural light intensity in the industrial plant area in real time, calculate the ambient light difference coefficient HJZD, and compare and analyze it with the first threshold Q1 to determine whether the natural light illumination in the industrial plant area is qualified and provide a strategy; The task adaptive monitoring module is used to calculate the task matching illumination coefficient ZYZx by real-time monitoring the task illumination requirements, actual illumination level, on-the-job personnel density and task load duration of the industrial plant area, and compare and analyze it with the second threshold Q2 to determine whether the illumination of the area is reasonably matched with the task requirements and provide a strategy; The global lighting load energy efficiency monitoring module is used to calculate the load balancing energy consumption coefficient FZNH by comprehensively monitoring the power levels, power change trends, historical cumulative energy consumption and reference value deviations of all areas of the industrial plant, and compare and analyze it with the third threshold Q3 to determine whether the collaborative load status of the industrial plant is qualified and provide a strategy.

[0006] Preferably, the data acquisition module includes an area division unit, a deployment unit and a collection unit; The area division unit is used to obtain the lighting group distribution map of the industrial plant in advance, divide the industrial plant into several areas, and mark them on the lighting group distribution map; The deployment unit is used to deploy an ambient light sensor, a power calculation device, an infrared sensing device and a meteorological data access terminal in the area; The collection unit is used to collect environmental data in real time through deployed equipment, including: natural light illumination, window area, window orientation parameters, climate interference factors and reflected light contribution value of the area; collected lighting data including: real-time illumination value of the area, target illumination requirement, real-time lighting power, power change rate and accumulated energy consumption value of the area; collected comprehensive behavior data including: number of people on duty in the area, work task type data and duration of low load in the area.

[0007] Preferably, the data processing module is used to perform feature normalization, noise filtering and time alignment processing on the collected environmental data, lighting data and behavioral comprehensive data by adopting multimodal feature fusion and time series interpolation algorithm, and obtain a structured input feature data set.

[0008] Preferably, the AI ​​illumination dynamic adjustment model establishment module is used to construct a deep learning model LightBalanceNet-Init that integrates natural light, artificial lighting and task demand characteristics through the structured input feature data set and historical operation and maintenance sample information in the industrial plant; taking regional natural light illumination, real-time artificial illumination, task type target illumination, dynamic changes in lighting power, load continuity and energy consumption records as input, extracting key features of environmental differences, task adaptability and load stability, and constructing an initial model with the ability to perceive the environment dynamically, adapt to task requirements and balance lighting energy consumption; model training process In the process, the window area and orientation, the task database, the number and arrangement of on-the-job personnel, and the external light disturbance factor are integrated to construct a multi-source joint training data set; a multi-channel convolutional neural network and an attention enhancement mechanism fusion structure are adopted to effectively extract the key influencing factors in the lighting feature maps and power change sequences of different areas; through continuous training and dynamic evolution of feature vectors, the model operates as an AI dynamic illumination adjustment model, and outputs intelligent dimming and energy-saving control for industrial plants. It has the ability to adaptively generate lighting strategies in multi-area, variable load, and different task scenarios, supporting plant-level energy optimization and continuous improvement of task lighting efficiency.

[0009] Preferably, the ambient light monitoring module includes a first calculation unit and a first analysis unit; The first calculation unit is used to calculate the ambient illumination difference coefficient HJZD by real-time monitoring of the natural light intensity and reflected light contribution of area z, combining the window area, azimuth and weather conditions in the area, and performing dimensionless processing.

[0010] Preferably, the first analysis unit is used to preset a first threshold Q1 in advance, and compare and analyze the ambient illumination difference coefficient HJZD with the first threshold Q1, and obtaining the first evaluation result includes: When the ambient illumination difference coefficient HJZD ≤ the first threshold Q1 When it reaches 50%, it means that the natural light illumination in area z is qualified at level one, and all light groups are turned off and switched to daylight following mode to utilize natural light; When the first threshold Q1 When 50% < ambient illumination difference coefficient HJZD ≤ first threshold Q1, it means that the natural light illumination of area z is qualified as level 2, and 10% to 30% of the lighting groups are turned on; When the ambient illumination difference coefficient HJZD> the first threshold Q1, it means that the natural light illumination of area z is unqualified, triggering the first warning instruction, starting the task matching illumination mechanism, and adjusting the illumination of the light group according to the task illumination requirement.

[0011] Preferably, the operation task adaptive monitoring module includes a second calculation unit and a second analysis unit; The second calculation unit is used to calculate the task matching illumination coefficient ZYZx after dimensionless processing by real-time monitoring of the task illumination requirements, actual illumination level, on-the-job personnel density and task load duration of area z when receiving the first warning instruction.

[0012] Preferably, the second analysis unit is used to preset a second threshold Q2 in advance, and compare and analyze the task matching illumination coefficient ZYZx with the second threshold Q2, and obtain the second evaluation result including: When the task matching illumination coefficient ZYZx ≥ the second threshold Q2 When the value is 130%, it indicates that there is a first-level deviation between the illumination of area z and the task requirement, and the illumination resources are redundant, triggering the second warning command to reduce the full-power lighting group to 30% to 50%; When the second threshold Q2 130%>task ​​matching illumination coefficient ZYZx≥second threshold Q2 80%, indicating that the illumination in area z is reasonably matched with the task requirements, and 60% to 70% of the lighting groups are turned on for continuous monitoring; When the task matching illumination coefficient ZYZx is less than the second threshold Q2 When it reaches 80%, it indicates that there is a secondary deviation between the illumination in area z and the task requirement, and the illumination load is insufficient, triggering the third warning instruction, turning on 80% to 100% of the lighting groups, and starting the coordinated control mechanism of the energy efficiency of the global lighting load.

[0013] Preferably, the global lighting load energy efficiency monitoring module includes a third calculation unit and a third analysis unit; The third calculation unit is used to calculate the load balancing energy consumption coefficient FZNH after dimensionless processing by comprehensively monitoring the power levels, power change trends, historical cumulative energy consumption and reference value deviations of all areas of the industrial plant when receiving the third early warning instruction.

[0014] Preferably, the third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the load balancing energy consumption coefficient FZNH with the third threshold Q3, and obtaining the third evaluation result includes: When the load balancing energy consumption coefficient FZNH ≤ the third threshold Q3, it indicates that the coordinated load status of the industrial plant is qualified, there is no risk of energy consumption deviation and dynamic anomaly, and continuous monitoring is required; When the load balancing energy consumption coefficient FZNH is greater than the third threshold value Q3, it indicates that the coordinated load status of the industrial plant is unqualified, and there is a risk of energy consumption deviation and dynamic anomaly. The fourth early warning instruction is triggered, and the illumination load distribution task is shared across regions. The illumination setting value of the center of gravity of the work surface is adjusted through shared control of boundary lighting fixtures; some lamp groups in area z are included in the dimming control sequence, and automatic illumination reduction control is implemented in different time periods, reducing it by 10% every 10 minutes, alleviating peak energy consumption loads and reducing the degree of imbalance.

[0015] The present invention provides a weak current intelligent lighting system with intelligent dimming and energy-saving control. It has the following beneficial effects: (1) This intelligent dimming and energy-saving control system for weak-current intelligent lighting, by deploying multiple types of sensor equipment such as light, power, infrared, and meteorological sensors in the divided areas of industrial plants, collects multi-dimensional information such as natural light, lighting, human behavior, and environmental interference in real time. It also uses feature fusion and time series interpolation algorithms to achieve normalization, filtering, and time alignment of multi-source heterogeneous data to construct a structured feature data set. This mechanism solves the problems of traditional systems with a single data source, high data noise interference, and poor timeliness, significantly improving the environmental perception accuracy and real-time response of the lighting control system.

[0016] (2) This intelligent dimming and energy-saving control system for weak-current lighting is based on structured data and historical sample information. It constructs a deep learning model, LightBalanceNet-Init, that integrates natural light illumination, lighting power dynamics, task requirements, and behavioral data. It also introduces a multi-channel convolutional neural network and attention mechanism to extract environmental differences, task adaptability, and energy consumption dynamics to achieve intelligent generation of lighting strategies. Compared with traditional preset rule control, this model has stronger generalization and adaptability, and can achieve dynamic matching and energy consumption balance between lighting and workload in complex and changing production scenarios.

[0017] (3) This intelligent dimming and energy-saving control system for weak-current intelligent lighting establishes three key evaluation indicators: the ambient illumination difference coefficient HJZD, the task matching illumination coefficient ZYZx, and the load balancing energy consumption coefficient FZNH. It conducts real-time quantitative analysis of natural light utilization, task adaptability, and lighting load balancing status, and introduces a threshold comparison mechanism for graded judgment and early warning triggering. This design breaks through the limitations of traditional lighting systems of "coarse-grained control and no feedback regulation" and achieves controllable, visual, and evaluable illumination zoning optimization and system load status, helping to reduce redundant lighting, alleviate load overload, and improve overall energy efficiency.

[0018] (4) Based on the evaluation results, the intelligent dimming and energy-saving control of the weak-current intelligent lighting system can adaptively generate regional lighting adjustment strategies, including daylight following mode, task illumination compensation mechanism, and cross-region load sharing dimming mechanism. Through boundary lighting sharing control, dimming reduction strategy and dynamic grouping of regional light groups, it can achieve refined control of first-level deviation, second-level deviation and load anomalies, effectively avoiding energy waste and insufficient illumination. This strategy system is highly flexible and scalable, and can support collaborative energy saving in multi-region heterogeneous scenarios, significantly improving the operating efficiency and green level of industrial plant lighting systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a block diagram and flow chart of the weak-current intelligent lighting system with intelligent dimming and energy-saving control of the present invention. DETAILED DESCRIPTION

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0021] Example 1 See also Figure 1 The present invention provides a weak current intelligent lighting system with intelligent dimming and energy-saving control, including a data acquisition module, a data processing module, an AI illumination dynamic adjustment model establishment module, an ambient light monitoring module, an operation task adaptive monitoring module and a global lighting load energy efficiency monitoring module; The data acquisition module is used to collect environmental data, lighting data and behavioral comprehensive data in real time by dividing the industrial plant into multiple marked areas and deploying light, power, infrared and meteorological sensing equipment in each area; The data processing module is used to normalize, filter and time-align the multi-source collected data using feature fusion and time series interpolation algorithms, and obtain a structured feature data set; The AI ​​illuminance dynamic adjustment model establishment module is used to build a deep learning model that integrates natural light, lighting power, and operational requirements based on structured feature dataset data and historical samples. It has environmental perception, task adaptation, and energy consumption balance capabilities, and realizes adaptive generation and energy-saving control of multi-area lighting strategies. The ambient light monitoring module is used to monitor the natural light intensity in the industrial plant area in real time, calculate the ambient light difference coefficient HJZD, and compare and analyze it with the first threshold Q1 to determine whether the natural light illumination in the industrial plant area is qualified and provide a strategy; The task adaptive monitoring module is used to calculate the task matching illumination coefficient ZYZx by real-time monitoring the task illumination requirements, actual illumination level, on-the-job personnel density and task load duration of the industrial plant area, and compare and analyze it with the second threshold Q2 to determine whether the illumination of the area is reasonably matched with the task requirements and provide a strategy; The global lighting load energy efficiency monitoring module is used to calculate the load balancing energy consumption coefficient FZNH by comprehensively monitoring the power levels, power change trends, historical cumulative energy consumption and reference value deviations of all areas of the industrial plant, and compare and analyze it with the third threshold Q3 to determine whether the collaborative load status of the industrial plant is qualified and provide a strategy.

[0022] In this embodiment, by constructing a multi-module collaborative architecture encompassing data acquisition, data processing, an AI-powered dynamic illumination adjustment model, ambient light monitoring, adaptive task monitoring, and global lighting load energy efficiency monitoring, a multi-dimensional, real-time perception and in-depth fusion analysis of natural light intensity, task requirements, and lighting load status within industrial plants is achieved. The system dynamically calculates the ambient illumination difference coefficient HJZD, the task matching illumination coefficient ZYZx, and the load balancing energy consumption coefficient FZNH. Based on the comparison results with multi-level thresholds, it generates an adaptive lighting adjustment strategy, significantly improving the matching between regional lighting and task behavior, optimizing lighting load distribution, and achieving the organic unity of global energy conservation and intelligent lighting control. This overcomes the technical bottlenecks of extensive control, delayed response, and high energy consumption of traditional lighting systems.

[0023] Example 2 This example is explained in Example 1. Figure 1 ,Specifically, the data acquisition module includes an area division unit, a deployment unit and a ,acquisition unit; The area division unit is used to obtain the lighting group distribution map of the industrial plant in advance, divide the industrial plant into several areas, and mark them on the lighting group distribution map; The deployment unit is used to deploy an ambient light sensor, a power calculation device, an infrared sensing device and a meteorological data access terminal in the area; The collection unit is used to collect environmental data in real time through deployed equipment, including: natural light illumination, window area, window orientation parameters, climate interference factors and reflected light contribution value of the area; collected lighting data including: real-time illumination value of the area, target illumination requirement, real-time lighting power, power change rate and accumulated energy consumption value of the area; collected comprehensive behavior data including: number of people on duty in the area, work task type data and duration of low load in the area.

[0024] In this embodiment, by introducing a regional division unit, a deployment unit, and a collection unit into the data acquisition module, refined spatial division and multi-dimensional information collection of the industrial plant lighting environment are achieved. The system not only accurately demarcates regional boundaries based on the distribution of lighting groups, but also deploys illumination, power, infrared, and meteorological sensing equipment within each area to comprehensively collect multi-source data such as natural light intensity, window structure parameters, climate interference factors, lighting energy consumption characteristics, and human work behavior. This ensures the comprehensiveness and real-time nature of the lighting system's input information, providing high-quality, structured data support for subsequent AI model development and intelligent strategy generation, significantly improving the system's perception accuracy and responsiveness to dynamic work scenarios and environmental changes.

[0025] Example 3 This example is explained in Example 2. Figure 1 Specifically, the data processing module is used to perform feature normalization, noise filtering and time alignment on the collected environmental data, lighting data and behavioral comprehensive data by adopting multimodal feature fusion and time series interpolation algorithm, and obtain a structured input feature data set.

[0026] In this embodiment, by introducing multimodal feature fusion and time interpolation algorithms in the data processing module, feature normalization, noise filtering and time alignment are performed on environmental data, lighting data and behavioral comprehensive data, which significantly improves the comparability and synergy between multi-source heterogeneous data, and solves the information bias and modeling error problems caused by inconsistent data formats and inconsistent sampling frequencies in traditional systems, thereby effectively improving the stability and accuracy of the subsequent AI illumination dynamic adjustment model during training and inference, and laying a solid data foundation for realizing high-precision and robust intelligent lighting control strategies.

[0027] Example 4 This example is explained in Example 3. Figure 1Specifically, the AI ​​illumination dynamic adjustment model establishment module is used to build a deep learning model LightBalanceNet-Init that integrates natural light, artificial lighting and task demand characteristics through the structured input feature data set and historical operation and maintenance sample information in the industrial plant; taking regional natural light illumination, real-time artificial illumination, task type target illumination, dynamic changes in lighting power, load continuity and energy consumption records as input, it extracts key features of environmental differences, task adaptability and load stability, and builds an initial model with the ability to perceive the environment dynamically, adapt to task requirements and balance lighting energy consumption; the model training process During the training process, the window area and orientation, the task database, the number and arrangement of on-the-job personnel, and the external light disturbance factors are integrated to construct a multi-source joint training dataset. A multi-channel convolutional neural network and an attention enhancement mechanism fusion structure are used to effectively extract the key influencing factors in the lighting feature maps and power change sequences of different areas. Through continuous training and dynamic evolution of feature vectors, the model operates as an AI dynamic illumination adjustment model, outputting intelligent dimming and energy-saving control for industrial plants. It has the ability to adaptively generate lighting strategies for multi-area, variable load, and different task scenarios, supporting plant-level energy optimization and continuous improvement of task lighting efficiency.

[0028] In this embodiment, by constructing a deep learning model LightBalanceNet-Init that integrates natural light, artificial lighting and work demand characteristics, and introducing a multi-channel convolutional neural network and attention enhancement mechanism structure, it is possible to accurately extract the key influencing factors in the lighting feature maps and power change sequences of different areas in industrial plants, and realize dynamic perception and task adaptation of multi-area, variable load and different task lighting scenes, effectively overcoming the problems of delayed response and poor adaptability of traditional lighting control strategies, significantly improving the accuracy and real-time performance of intelligent dimming strategies, and thus achieving coordinated optimization of energy-saving control and work efficiency.

[0029] Example 5 This example is explained in Example 4. Figure 1 ,Specifically, the environmental light monitoring module includes a first calculation unit and a first analysis unit; The first calculation unit is used to calculate the ambient illumination difference coefficient HJZD by real-time monitoring of the natural light intensity and reflected light contribution of area z, combining the window area, azimuth and weather conditions in the area, and performing dimensionless processing. The formula is as follows: ; Where, represents the natural light intensity at time t, Represents the residual light reflection value at time t, represents the required illumination at time t in area z, represents the total projected area of ​​the windows in region z, represents the angle between the window normal of area z and the direction of incidence of the sun, represents the projected building area of ​​region z, Indicates the weather shielding factor. Common values ​​are: 0.1 for sunny days, 0.5 for cloudy days, and 0.8 for rainy days. w1, w2, and w3 represent weight coefficients. 、 and ,and .

[0030] In this embodiment, by constructing an environmental illumination difference evaluation coefficient based on multi-dimensional parameter fusion The calculation mechanism integrates real-time natural light intensity, reflected light contribution value, window structure parameters and weather shielding factors to comprehensively evaluate the matching degree between the natural lighting in the factory area and the target illumination of the operation. By comparing with the set threshold, it can realize dynamic judgment of the demand for natural light supplement, improve the system's response ability to external environmental disturbances, avoid unnecessary artificial lighting output, and thus significantly enhance the energy-saving effect and operational adaptability of the intelligent lighting system.

[0031] Example 6 This example is an explanation of Example 5. Figure 1 Specifically, the first analysis unit is used to preset a first threshold Q1 in advance, and compare and analyze the ambient illumination difference coefficient HJZD with the first threshold Q1, and obtain the first evaluation result including: When the ambient illumination difference coefficient HJZD ≤ the first threshold Q1 When it reaches 50%, it means that the natural light illumination in area z is qualified at level one, and all light groups are turned off and switched to daylight following mode to utilize natural light; When the first threshold Q1 When 50% < ambient illumination difference coefficient HJZD ≤ first threshold Q1, it means that the natural light illumination of area z is qualified as level 2, and 10% to 30% of the lighting groups are turned on; When the ambient illumination difference coefficient HJZD> the first threshold Q1, it means that the natural light illumination of area z is unqualified, triggering the first warning instruction, starting the task matching illumination mechanism, and adjusting the illumination of the light group according to the task illumination requirement.

[0032] In this embodiment, a comparison and analysis mechanism is established between the ambient illumination difference coefficient HJZD and the classification threshold Q1 to achieve a graded assessment of the natural lighting status of the area and precise control of the lighting strategy. This mechanism can automatically identify the qualified illumination level based on the degree to which natural light meets the illumination requirements of the task, and intelligently switch between three modes: daylight following, partial lighting, or task illumination response. This significantly reduces unnecessary lighting on time, improves the intelligent response and energy saving effect of the lighting system, and ensures that the working area always maintains a reasonable illumination level, improving the safety and energy efficiency management level of industrial plant operations. Specific embodiments are shown in the following table:

[0033] Example 7 This example is an explanation of Example 6. Figure 1 ,Specifically, the operation task adaptive monitoring module includes a second ,computing unit and a second analyzing unit; The second calculation unit is used to calculate the task matching illumination coefficient ZYZx after dimensionless processing by real-time monitoring the illumination requirement, actual illumination level, on-the-job personnel density and task load duration of the task in area z upon receiving the first warning instruction. The formula is as follows: ; Where, represents the illumination value of area z at time t, represents the target illumination value of the task at time t in area z, represents the number of people in area z at time t, represents the maximum operator capacity of area z, represents the base of the natural constants, It represents the continuous low-load operation time of area z at time t. Indicates the low load critical threshold, Represents the slope factor of the adjustment function, which is obtained by model training. a1, a2 and a3 represent weight coefficients. 、 and ,and .

[0034] This embodiment constructs a multi-factor calculation mechanism for task-matched illumination coefficients (ZYZx), integrating key operational parameters such as the deviation between real-time and target illumination, on-duty personnel density, and duration of low loads. This allows for a dynamic assessment of the degree to which an area's current illumination matches actual task requirements. Compared to traditional strategies based on a single illumination level, this mechanism accurately models illumination rationality under varying tasks and loads, avoiding energy waste caused by redundant illumination and preventing operational efficiency from being impacted by insufficient illumination.

[0035] Example 8 This example is explained in Example 7. Figure 1 Specifically, the second analysis unit is used to preset a second threshold Q2 in advance, and compare and analyze the task matching illumination coefficient ZYZx with the second threshold Q2, and obtain the second evaluation result including: When the task matching illumination coefficient ZYZx ≥ the second threshold Q2 When the value is 130%, it indicates that there is a first-level deviation between the illumination of area z and the task requirement, and the illumination resources are redundant, triggering the second warning command to reduce the full-power lighting group to 30% to 50%; When the second threshold Q2 130%>task ​​matching illumination coefficient ZYZx≥second threshold Q2 80%, indicating that the illumination in area z is reasonably matched with the task requirements, and 60% to 70% of the lighting groups are turned on for continuous monitoring; When the task matching illumination coefficient ZYZx is less than the second threshold Q2 When it reaches 80%, it indicates that there is a secondary deviation between the illumination in area z and the task requirement, and the illumination load is insufficient, triggering the third warning instruction, turning on 80% to 100% of the lighting groups, and starting the coordinated control mechanism of the energy efficiency of the global lighting load.

[0036] In this embodiment, by setting a multi-level threshold judgment mechanism for matching the task illumination coefficient ZYZx, it is possible to finely identify and grade the degree of deviation between the illumination status in the industrial plant area and the actual operation requirements. This mechanism not only actively reduces the lighting power to achieve energy-saving control when there is illumination redundancy, but also quickly increases the illumination when illumination is insufficient and links the coordinated adjustment of global lighting resources, effectively avoiding energy waste and reduced operating efficiency caused by illumination imbalance, and significantly improving the intelligent response capability and adaptability of the lighting system to the operating environment. Specific embodiments are shown in the following table:

[0037] Example 9 This example is explained in Example 8. Figure 1 ,Specifically, the global lighting load energy efficiency monitoring module includes a third calculation unit and a third analysis unit; The third calculation unit is used to calculate the load balancing energy consumption coefficient FZNH after dimensionless processing by comprehensively monitoring the power levels, power change trends, and historical cumulative energy consumption deviations from reference values ​​in all areas of the industrial plant upon receiving the third early warning instruction. The formula is as follows: ; Where N represents the number of industrial plant areas, represents the actual lighting power in the zth region at time t, represents the average lighting power of all areas at time t, represents the rate of change of the lighting power in area z at time t, Indicates the total electricity consumed by lighting in area z in the past 24 hours. represents the reference standard energy consumption of the zth area, represents the energy consumption deviation rate, 、 and represents the weight coefficient, 、 and ,and .

[0038] In this embodiment, by introducing the load-balancing energy consumption coefficient FZNH, the present invention can dynamically assess the distribution rationality of lighting power levels and the degree of energy consumption deviation in each area of ​​the industrial plant after receiving the third early warning instruction, identifying areas of abnormally high energy consumption and their power fluctuation trends. This indicator integrates the multi-dimensional characteristics of real-time power, historical cumulative energy consumption, and standard deviation, and possesses excellent timeliness and sensitivity. It facilitates the precise quantification and coordinated regulation of the energy efficiency status of the global lighting system, providing a data basis for subsequent energy-saving strategy optimization and lighting load balancing, significantly improving the overall operational efficiency and energy utilization of the plant-level lighting system.

[0039] Example 10 This example is explained in Example 9. Figure 1 Specifically, the third analysis unit is used to preset a third threshold Q3 in advance, and compare and analyze the load balancing energy consumption coefficient FZNH with the third threshold Q3, and obtain a third evaluation result including: When the load balancing energy consumption coefficient FZNH ≤ the third threshold Q3, it indicates that the coordinated load status of the industrial plant is qualified, there is no risk of energy consumption deviation and dynamic anomaly, and continuous monitoring is required; When the load balancing energy consumption coefficient FZNH is greater than the third threshold value Q3, it indicates that the coordinated load status of the industrial plant is unqualified, and there is a risk of energy consumption deviation and dynamic anomaly. The fourth early warning instruction is triggered, and the illumination load distribution task is shared across regions. The illumination setting value of the center of gravity of the work surface is adjusted through shared control of boundary lighting fixtures; some lamp groups in area z are included in the dimming control sequence, and automatic illumination reduction control is implemented in different time periods, reducing it by 10% every 10 minutes, alleviating peak energy consumption loads and reducing the degree of imbalance.

[0040] In this embodiment, by setting a third threshold Q3 and performing real-time comparison and analysis of the load-balancing energy consumption coefficient FZNH, the present invention can promptly identify uneven power loads and abnormal energy consumption within the global lighting system of an industrial plant. Once the threshold is exceeded, the system intelligently triggers a fourth warning instruction, implementing cross-regional illumination load sharing and coordinated control of boundary lighting. This, combined with a time-based, decremental dimming mechanism, dynamically alleviates local peak energy consumption pressures. This mechanism effectively prevents local overloads and overall system efficiency decline, achieving global coordination of lighting power and energy consumption optimization, improving plant-level energy balance and intelligent dimming responsiveness. Specific examples are shown in the following table:

[0041] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0042] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Intelligent dimming and energy-saving control of weak current intelligent lighting system, characterized by: It includes data acquisition module, data processing module, AI illumination dynamic adjustment model establishment module, ambient light monitoring module, task adaptive monitoring module and global lighting load energy efficiency monitoring module; The data acquisition module is used to collect environmental data, lighting data and behavioral comprehensive data in real time by dividing the industrial plant into multiple marked areas and deploying light, power, infrared and meteorological sensing equipment in each area; The data processing module is used to normalize, filter and time-align the multi-source collected data using feature fusion and time series interpolation algorithms, and obtain a structured feature data set; The AI ​​illuminance dynamic adjustment model establishment module is used to build a deep learning model that integrates natural light, lighting power, and operational requirements based on structured feature dataset data and historical samples. It has environmental perception, task adaptation, and energy consumption balance capabilities, and realizes adaptive generation and energy-saving control of multi-area lighting strategies. The ambient light monitoring module is used to monitor the natural light intensity in the industrial plant area in real time, calculate the ambient light difference coefficient HJZD, and compare and analyze it with the first threshold Q1 to determine whether the natural light illumination in the industrial plant area is qualified and provide a strategy; The task adaptive monitoring module is used to calculate the task matching illumination coefficient ZYZx by real-time monitoring the task illumination requirements, actual illumination level, on-the-job personnel density and task load duration of the industrial plant area, and compare and analyze it with the second threshold Q2 to determine whether the illumination of the area is reasonably matched with the task requirements and provide a strategy; The global lighting load energy efficiency monitoring module is used to calculate the load balancing energy consumption coefficient FZNH by comprehensively monitoring the power levels, power change trends, historical cumulative energy consumption and reference value deviations of all areas of the industrial plant, and compare and analyze it with the third threshold Q3 to determine whether the collaborative load status of the industrial plant is qualified and provide a strategy.

2. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 1 is characterized in that: The data acquisition module includes an area division unit, a deployment unit and a collection unit; The area division unit is used to obtain the lighting group distribution map of the industrial plant in advance, divide the industrial plant into several areas, and mark them on the lighting group distribution map; The deployment unit is used to deploy an ambient light sensor, a power calculation device, an infrared sensing device and a meteorological data access terminal in the area; The collection unit is used to collect environmental data in real time through deployed equipment, including: natural light illumination, window area, window orientation parameters, climate interference factors and reflected light contribution value of the area; collected lighting data including: real-time illumination value of the area, target illumination requirement, real-time lighting power, power change rate and accumulated energy consumption value of the area; collected comprehensive behavior data including: number of people on duty in the area, work task type data and duration of low load in the area.

3. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 2 is characterized in that: The data processing module is used to perform feature normalization, noise filtering and time alignment processing on the collected environmental data, lighting data and behavioral comprehensive data by adopting multimodal feature fusion and time series interpolation algorithm, and obtain a structured input feature data set.

4. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 3 is characterized in that: The AI ​​illumination dynamic adjustment model establishment module is used to build a deep learning model LightBalanceNet-Init that integrates natural light, artificial lighting and task demand characteristics through the structured input feature data set and historical operation and maintenance sample information in the industrial plant; it uses regional natural light illumination, real-time artificial illumination, task type target illumination, dynamic changes in lighting power, load continuity and energy consumption records as input to extract key features of environmental differences, task adaptability and load stability, and build an initial model with the ability to perceive the environment dynamically, adapt to task requirements and balance lighting energy consumption; during the model training process, A multi-source joint training dataset is constructed by integrating the window area and orientation, the task database, the number and arrangement of on-the-job personnel, and the external light disturbance factor. A multi-channel convolutional neural network and an attention enhancement mechanism fusion structure are used to effectively extract the key influencing factors in the lighting feature maps and power change sequences of different areas. Through continuous training and the dynamic evolution of feature vectors, the model operates as an AI dynamic illumination adjustment model, outputting intelligent dimming and energy-saving control for industrial plants. It has the ability to adaptively generate lighting strategies for multi-area, variable load, and different task scenarios, supporting plant-level energy optimization and the continuous improvement of task lighting efficiency.

5. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 4 is characterized in that: The ambient light monitoring module includes a first calculation unit and a first analysis unit; The first calculation unit is used to calculate the ambient illumination difference coefficient HJZD by real-time monitoring of the natural light intensity and reflected light contribution of area z, combining the window area, azimuth and weather conditions in the area, and performing dimensionless processing.

6. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 5 is characterized in that: The first analysis unit is used to preset a first threshold Q1 in advance, and compare and analyze the ambient illumination difference coefficient HJZD with the first threshold Q1, and obtain a first evaluation result including: When the ambient illumination difference coefficient HJZD ≤ the first threshold Q1 When it reaches 50%, it means that the natural light illumination in area z is qualified at level one, and all light groups are turned off and switched to daylight following mode to utilize natural light; When the first threshold Q1 When 50% < ambient illumination difference coefficient HJZD ≤ first threshold Q1, it means that the natural light illumination of area z is qualified as level 2, and 10% to 30% of the lighting groups are turned on; When the ambient illumination difference coefficient HJZD> the first threshold Q1, it means that the natural light illumination of area z is unqualified, triggering the first warning instruction, starting the task matching illumination mechanism, and adjusting the illumination of the light group according to the task illumination requirement.

7. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 6 is characterized in that: The operation task adaptive monitoring module includes a second calculation unit and a second analysis unit; The second calculation unit is used to calculate the task matching illumination coefficient ZYZx after dimensionless processing by real-time monitoring of the task illumination requirements, actual illumination level, on-the-job personnel density and task load duration of area z when receiving the first warning instruction.

8. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 7 is characterized in that: The second analysis unit is used to preset a second threshold Q2 in advance, and compare and analyze the task matching illumination coefficient ZYZx with the second threshold Q2 to obtain a second evaluation result including: When the task matching illumination coefficient ZYZx ≥ the second threshold Q2 When the value is 130%, it indicates that there is a first-level deviation between the illumination of area z and the task requirement, and the illumination resources are redundant, triggering the second warning command to reduce the full-power lighting group to 30% to 50%; When the second threshold Q2 130%>task ​​matching illumination coefficient ZYZx≥second threshold Q2 80%, indicating that the illumination in area z is reasonably matched with the task requirements, and 60% to 70% of the lighting groups are turned on for continuous monitoring; When the task matching illumination coefficient ZYZx is less than the second threshold Q2 When it reaches 80%, it indicates that there is a secondary deviation between the illumination in area z and the task requirement, and the illumination load is insufficient, triggering the third warning instruction, turning on 80% to 100% of the lighting groups, and starting the coordinated control mechanism of the energy efficiency of the global lighting load.

9. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 8, characterized in that: The global lighting load energy efficiency monitoring module includes a third calculation unit and a third analysis unit; The third calculation unit is used to calculate the load balancing energy consumption coefficient FZNH after dimensionless processing by comprehensively monitoring the power levels, power change trends, historical cumulative energy consumption and reference value deviations of all areas of the industrial plant when receiving the third early warning instruction.

10. The intelligent dimming and energy-saving control weak current intelligent lighting system according to claim 9, characterized in that: The third analysis unit is configured to preset a third threshold Q3 in advance, and compare and analyze the load balancing energy consumption coefficient FZNH with the third threshold Q3, and obtain a third evaluation result including: When the load balancing energy consumption coefficient FZNH ≤ the third threshold Q3, it indicates that the coordinated load status of the industrial plant is qualified, there is no risk of energy consumption deviation and dynamic abnormality, and continuous monitoring is required; When the load balancing energy consumption coefficient FZNH is greater than the third threshold value Q3, it indicates that the coordinated load status of the industrial plant is unqualified, and there is a risk of energy consumption deviation and dynamic anomaly. The fourth early warning instruction is triggered, and the illumination load distribution task is shared across regions. The illumination setting value of the center of gravity of the work surface is adjusted through shared control of boundary lighting fixtures; some lamp groups in area z are included in the dimming control sequence, and automatic illumination reduction control is implemented in different time periods, reducing it by 10% every 10 minutes, alleviating peak energy consumption loads and reducing the degree of imbalance.

Images